Ultra-Low-Bitrate Compression of Visual Content with Generative AI: Toward Semantic Visual Communication
The demand for high-quality and immersive visual content continues to outpace the capacity of current 5G and future 6G networks, making compression an essential component of visual communication. Despite major advances in video coding over the past decades, key challenges such as latency, energy efficiency, scalability, and robustness remain unresolved.
This talk will focus on one of these challenges: achieving effective compression at extremely low bitrates, where traditional codecs fail to preserve perceptual quality. Learning-based approaches enable substantial bandwidth reduction by exploiting the structure and semantics of visual content and can operate in a generative regime, where visual data are reconstructed by conditioning a trained model on compact latent or semantic representations. However, efficiently navigating the rate–distortion–perception trade-off with these models remains a major open problem.
I will illustrate these ideas through two examples: generative face video coding (GFVC), where realistic talking-face motion and texture can be synthesized from compact transmitted features, and generative 3D point cloud compression, where compact embeddings are used to guide a diffusion-based reconstruction. I will conclude by discussing how these concepts extend to semantic and task-oriented video communication, which generalizes traditional paradigms and opens new perspectives in this evolving field.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- No. 555 Tianjiao Road, Building 3C, 8th Floor, Zhongdian Sunshine Information Port
- Chengdu, Sichuan
- China
- Building: Huang Danian Tea & Thinking House (UESTC)
Speakers
Ultra-Low-Bitrate Compression of Visual Content with Generative AI: Toward Semantic Visual Communication
Biography:
Giuseppe Valenzise (giuseppe.valenzise@l2s.centralesupelec.fr) is a CNRS researcher at Université Paris-Saclay, CNRS, Central-eSupélec, in the Laboratoire des Signaux et Systémes, where he is currently the head of the Multimedia and Networking team. He is the Editor in Chief of the EURASIP Journal on Image and Video Processing. Giuseppe obtained his Ph.D. degree from Politecnico di Milano, Italy, in 2011. He joined the French Centre National de la Recherche Scientifique (CNRS) in 2012. His research interests span different fields of image and video processing, including traditional and learning-based image and video compression, light fields and point cloud coding, image/ video quality assessment, high dynamic range imaging and applications of machine learning to image and video analysis. He has co-authored one book and over 130 research publications. He received the EURASIP Early Career Award in 2018 for significant contributions to video coding and analysis. Giuseppe serves/has served as Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Image Processing (outstanding editorial board member award in 2022 and 2023), Elsevier Signal Processing: Image communication. He is the Chair of the Multimedia Signal Processing (MMSP) technical committee of the IEEE Signal Processing Society. He is/was also an elected member of the Multimedia Systems and Applications (MSA) technical committee of the IEEE Circuits and Systems Society, of the MMSP and IVMSP technical committees of the IEEE Signal Processing Society, and of the Technical Area Committee on Visual Information Processing of EURASIP. Giuseppe is one of the general co-chairs of the IEEE Int. Conference on Multimedia&Expo (ICME) 2025, held in Nantes, France.